© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76075
    Prev
    Next
    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.56
    cembre
    -0.51
    posedge
    -0.50
    Portale
    -0.49
    PreferredItem
    -0.48
     LUMP
    -0.48
    prüche
    -0.47
    xically
    -0.45
    CompilerServices
    -0.45
    tened
    -0.44
    POSITIVE LOGITS
    outs
    0.79
    -
    0.78
    about
    0.75
    overs
    0.74
    offs
    0.71
    bys
    0.71
    ups
    0.69
    through
    0.69
     overs
    0.69
     offs
    0.68
    Activations Density 0.017%

    No Known Activations